SENSOR: 能動的センシングによる第三者視点の模倣学習
SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring
視点のずれが大きい模倣学習において、カメラを能動的に動かして専門家の視点に合わせるモデルベース手法SENSORを提案し、視覚移動タスクで有効性を示した。
著者: Kaichen Huang, Minghao Shao, Shenghua Wan, Hai-Hang Sun, Shuai Feng, Le Gan, De-Chuan Zhan
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by domain alignment, which incurs extra computation and storage costs, and these methods fail to handle the \textit{hard cases} where the viewpoint gap is too large. To alleviate the above problems, we introduce active sensoring in the visual IL setting and propose a model-based SENSory imitatOR (SENSOR) to automatically change the agent's perspective to match the expert's. SENSOR jointly learns a world model to capture the dynamics of latent states, a sensor policy to control the camera, and a motor policy to control the agent. Experiments on visual locomotion tasks show that SENSOR can efficiently simulate the expert's perspective and strategy, and outperforms most baseline methods.
